Learning the Degradation Distribution for Blind Image Super-Resolution | |
Luo, Zhengxiong1,2,3![]() ![]() ![]() ![]() | |
2022-06 | |
会议名称 | IEEE Conference of Computer Vision and Pattern Recognition |
会议日期 | 2022-6 |
会议地点 | 美国新奥尔良 |
出版者 | IEEE |
摘要 | Synthetic high-resolution (HR) & low-resolution (LR) pairs are widely used in existing super-resolution (SR) methods. To avoid the domain gap between synthetic and test images, most previous methods try to adaptively learn the synthesizing (degrading) process via a deterministic model. However, some degradations in real scenarios are stochastic and cannot be determined by the content of the image. These deterministic models may fail to model the random factors and content-independent parts of degradations, which will limit the performance of the follow- ing SR models. In this paper, we propose a probabilistic degradation model (PDM), which studies the degradation D as a random variable, and learns its distribution by modeling the mapping from a priori random variable z to D. Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones. Extensive experiments have demonstrated that our degradation model can help the SR model achieve better performance on different datasets. |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51939 |
专题 | 模式识别实验室 |
通讯作者 | Huang, Yan |
作者单位 | 1.University of Chinese Academy of Sciences (UCAS) 2.National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC) 3.Institute of Automation, Chinese Academy of Sciences (CASIA) |
第一作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
通讯作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Luo, Zhengxiong,Huang, Yan,Li, Shang,et al. Learning the Degradation Distribution for Blind Image Super-Resolution[C]:IEEE,2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
2022 - Learning the (4811KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论